A pedestrian detecting system includes a depth capturing unit, an image capturing unit and a composite processing unit. The depth capturing unit is configured to detect and obtain spatial information of a target object. The image capturing unit is configured to capture an image of the target object and recognize the image, thereby obtaining image feature information of the target object. The composite processing unit is electrically connected to the depth capturing unit and the image capturing unit, wherein the composite processing unit is configured to receive the spatial information and the image feature information and to perform a scoring scheme to detect and determine if the target object is a pedestrian. The scoring scheme performs weighted scoring on a spatial confidence and an appearance confidence to obtain a composite scoring value to determine if the target object is the pedestrian.
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
2. The pedestrian detecting system of claim 1 , further comprising an image processing apparatus, wherein the image processing apparatus obtains an intermediately-illuminated image region of the target object recognized by the camera, and retains the image feature information of the intermediately-illuminated image region, wherein an illuminance of the intermediately-illuminated image region is from 10 to 80000 lux.
The pedestrian detection system, which uses a depth sensor for spatial information and a camera for image feature information to score and determine if a target object is a pedestrian, further incorporates an image processing component. This component isolates a specific image region of the target object, termed the "intermediately-illuminated" region, from the camera's input. The system then specifically retains the image feature information from this intermediately-illuminated region, where the illumination level is between 10 and 80000 lux. This focuses image processing on a specific lighting range.
3. The pedestrian detecting system of claim 2 , wherein the image processing apparatus obtains the intermediately-illuminated image region by using a Histogram of Oriented Gradient (HOG) and a Logarithm Weighted Pattern (LWP).
The pedestrian detection system, which uses a depth sensor for spatial information and a camera with an image processing component to score and determine if a target object is a pedestrian, isolates an "intermediately-illuminated" image region (10-80000 lux) and analyzes this region using Histogram of Oriented Gradients (HOG) and Logarithm Weighted Pattern (LWP) algorithms. HOG captures edge and shape information. LWP captures texture information. These two algorithms are applied to specifically analyze the features present in the intermediately illuminated region, extracting relevant data for pedestrian classification.
4. The pedestrian detecting system of claim 3 , wherein the operation of the Logarithm Weighted Pattern comprises capturing an image intensity variance of the target object, performing a logarithm operation and obtaining a portion of the image feature information.
The pedestrian detection system, which uses a depth sensor for spatial information and a camera with an image processing component to score and determine if a target object is a pedestrian, analyzes an "intermediately-illuminated" image region using HOG and LWP. The Logarithm Weighted Pattern (LWP) component operates by capturing the variance in image intensity across the target object within the intermediately illuminated region. It then performs a logarithm operation on these intensity variances. The result of this logarithm operation is then used as a portion of the image feature information used to determine if the target object is a pedestrian. This captures texture and subtle lighting changes.
5. The pedestrian detecting system of claim 1 , wherein the spatial information comprises a coordinate of the target object and a distance between the target object and a vehicle.
The pedestrian detection system uses a depth sensor to obtain spatial information and a camera to obtain image feature information to score and determine if a target object is a pedestrian. The spatial information obtained by the depth sensor specifically includes the coordinate of the target object in space, and the distance between the target object and the vehicle equipped with the pedestrian detection system. These parameters contribute to evaluating spatial confidence within a scoring scheme to determine if the target object is a pedestrian.
6. The pedestrian detecting system of claim 5 , wherein the scoring scheme uses a Gaussian function to obtain a matching probability between the image of the target object and the distance, thereby obtaining the spatial confidence.
The pedestrian detection system uses a depth sensor to obtain spatial information (including target object coordinates and distance to vehicle) and a camera to obtain image feature information to score and determine if a target object is a pedestrian. The scoring scheme, which weighs spatial and appearance confidence, calculates the spatial confidence by using a Gaussian function to determine a matching probability between the image of the target object (captured by the camera) and the distance to the object (measured by the depth sensor). The output of the Gaussian function is used as the spatial confidence score.
8. The pedestrian detecting system of claim 7 , wherein the intermediately-illuminated image region of the target object is obtained under a luminance greater than 10 lux.
The pedestrian detection system uses a depth sensor for spatial information and a camera for image feature information to score and determine if a target object is a pedestrian. The image processing apparatus obtains an intermediately-illuminated image region of the target object recognized by the camera, and retains the image feature information of the intermediately-illuminated image region. This intermediately-illuminated image region is obtained specifically under a luminance greater than 10 lux.
9. The pedestrian detecting system of claim 7 , wherein the image processing apparatus obtains the intermediately-illuminated image region through a Histogram of Oriented Gradient (HOG) and a Logarithm Weighted Pattern (LWP).
The pedestrian detection system uses a depth sensor for spatial information and a camera for image feature information to score and determine if a target object is a pedestrian. The image processing apparatus obtains an intermediately-illuminated image region of the target object recognized by the camera, and retains the image feature information of the intermediately-illuminated image region. The image processing apparatus obtains the intermediately-illuminated image region through the use of both a Histogram of Oriented Gradient (HOG) and a Logarithm Weighted Pattern (LWP). These are used to extract features from the intermediate illuminated image.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
December 30, 2014
August 8, 2017
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.